@inproceedings{d5bac5a341c3465f9fdfde212e7f4cb0,
title = "Network-aware multiway join for MapReduce",
abstract = "MapReduce is an effective tool for processing large amounts of data in parallel using a cluster of processors or computers. One common data processing task is the join operation, which combines two or more datasets based on values common to each. In this paper, we present a network aware multi-way join for MapReduce(NAMM) that improves performance by redistributing the workload amongst reducers. NAMM achieves this by redistributing tuples directly between reducers with an intelligent network aware algorithm. We show that our presented technique has significant potential to minimize the time required to join multiple datasets.",
keywords = "Hadoop, MapReduce, Multiway Join, Workload Redistribution",
author = "Kenn Slagter and Hsu, \{Ching Hsien\} and Chung, \{Yeh Ching\} and Park, \{Jong Hyuk\}",
year = "2013",
doi = "10.1007/978-3-642-38027-3\_8",
language = "English",
isbn = "9783642380266",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "73--80",
booktitle = "Grid and Pervasive Computing - 8th International Conference, GPC 2013 and Colocated Workshops, Proceedings",
note = "8th International Conference on Grid and Pervasive Computing, GPC 2013 ; Conference date: 09-05-2013 Through 11-05-2013",
}